© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3679
    Prev
    Next
    INDEX
    Explanations

    elements related to spatial properties and distributions in physical or experimental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Spatial properties or distributions

    np_acts-logits-general · gemini-2.0-flash

    spatial maps and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.41
    ьаж
    -0.36
     Accesat
    -0.34
     roue
    -0.34
     Obras
    -0.34
     dioses
    -0.33
     puerta
    -0.33
    switch
    -0.32
    ParallelGroup
    -0.32
     Majesté
    -0.32
    POSITIVE LOGITS
    IntoConstraints
    0.80
     areas
    0.71
     regions
    0.63
     Areas
    0.63
     zones
    0.62
    setVerticalGroup
    0.61
    areas
    0.60
     neighborhoods
    0.60
    Areas
    0.58
     patches
    0.57
    Activations Density 1.499%

    No Known Activations